Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1680 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1167588 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1582. Min Act: -0.0001

Data Index: 866239 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1051079 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1159. Min Act: -0.0002

Data Index: 697678 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1154. Min Act: -0.0002

Data Index: 356624 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1188. Min Act: -0.0001

Data Index: 648941 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1364. Min Act: -0.0001

Data Index: 641833 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1074. Min Act: -0.0001

Data Index: 818418 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1128. Min Act: -0.0001

Data Index: 945486 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1177. Min Act: -0.0001

Data Index: 491914 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1164. Min Act: -0.0001

Data Index: 76538 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1078. Min Act: -0.0001

Data Index: 687788 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1212861 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1109. Min Act: -0.0001

Data Index: 888927 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1028. Min Act: -0.0001

Data Index: 342728 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1048. Min Act: -0.0002

Data Index: 488595 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1025. Min Act: -0.0002

Data Index: 632776 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1058. Min Act: -0.0001

Data Index: 484576 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1001. Min Act: -0.0001

Data Index: 283439 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.1582. Min Range: -0.1582

Max Act: 0.1047. Min Act: -0.0001

Data Index: 902726 (C4 (Web Text))

Max Activating Token Index: 516